© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 16026
    Prev
    Next
    INDEX
    Explanations

    quantitative values or numerical sums

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of sum or total

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surn
    -0.79
     tradem
    -0.72
     clipboard
    -0.68
     blinking
    -0.66
    ussen
    -0.65
     foreclosure
    -0.63
     browsers
    -0.61
     blocked
    -0.61
     Lyft
    -0.61
     preferred
    -0.60
    POSITIVE LOGITS
     sum
    1.32
    mits
    1.17
    ming
    1.09
    sum
    1.05
    Sum
    0.88
     Sum
    0.85
     attRot
    0.83
     sums
    0.83
    mers
    0.81
    atsu
    0.81
    Activations Density 0.006%

    No Known Activations